# An expert-guided machine-learning approach to estimate the incidence, risk and harms associated with diagnostic delays for infectious diseases.

> **NIH AHRQ R01** · UNIVERSITY OF IOWA · 2020 · $496,235

## Abstract

Project Summary / Abstract
Diagnostic errors are increasingly recognized as a cause of pain, suffering and increased
healthcare costs. Diagnostic delays are an important class of diagnostic errors. While many
diagnostic errors occur in hospital settings, emergency departments visits may be especially
important to consider because they treat critically ill patients and because most decisions to
admit patients to the hospital are made in emergency departments. Thus, to enable a more
complete understanding of diagnostic delays requires consideration of healthcare visits across a
range of healthcare settings including clinic visits, emergency department visits and
hospitalizations.
Delays in diagnosing infectious diseases are important to consider. For contagious infectious
diseases, diagnostic delays increase the risk of additional exposures, potentially generating
more cases. Second, many infectious diseases can be effectively treated, but even short delays
in treatment lead to worse clinical outcomes. However, with the exception of a few infectious
diseases (e.g., tuberculosis), diagnostic delays for infectious diseases are understudied. Thus,
there is a critical need to investigate the incidence, risk factors and clinical impact for diagnostic
delays for infectious diseases.
The overarching goal of our research is to investigate diagnostic delays associated with
infectious diseases using existing data along with methods from the fields of computer science
and statistics. While our research relies upon “big data”, we will also use clinical experts to
review and contribute to all of our results. Our subject matter experts incorporate expertise in
infectious diseases, emergency medicine, acute care, medical education, diagnostic reasoning,
healthcare epidemiology, public health, industry, and professional infectious disease societies.
Specifically, we will 1) determine the incidence of diagnostic delays for a wide range of
infectious diseases; 2) identify the risk factors associated with diagnostic delays for infectious
diseases that are frequently delayed or have serious outcomes; and 3) estimate the impact of
diagnostic delays in terms of healthcare costs and mortality. With our data, methods and clinical
experts, we will be able to translate our results into future interventions designed to decrease
diagnostic delays and improve healthcare outcomes. In addition, while our proposal focuses on
infectious diseases, the methods and approaches that we will develop can be adopted to
investigate non-infectious diseases and conditions.

## Key facts

- **NIH application ID:** 10017203
- **Project number:** 5R01HS027375-02
- **Recipient organization:** UNIVERSITY OF IOWA
- **Principal Investigator:** Jennifer L. Kuntz
- **Activity code:** R01 (R01, R21, SBIR, etc.)
- **Funding institute:** AHRQ
- **Fiscal year:** 2020
- **Award amount:** $496,235
- **Award type:** 5
- **Project period:** 2019-09-30 → 2022-09-29

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10017203

## Citation

> US National Institutes of Health, RePORTER application 10017203, An expert-guided machine-learning approach to estimate the incidence, risk and harms associated with diagnostic delays for infectious diseases. (5R01HS027375-02). Retrieved via AI Analytics 2026-05-23 from https://api.ai-analytics.org/grant/nih/10017203. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*